A case study

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

## keep the school names with white spaces
dta <- read.csv("nzSchools.csv", as.is=2)

##檢視資料
str(dta)

## 'data.frame':    2571 obs. of  6 variables:
##  $ ID  : int  1015 1052 1062 1092 1130 1018 1029 1030 1588 1154 ...
##  $ Name: chr  "Hora Hora School" "Morningside School" "Onerahi School" "Raurimu Avenue School" ...
##  $ City: Factor w/ 541 levels "Ahaura","Ahipara",..: 533 533 533 533 533 533 533 533 533 533 ...
##  $ Auth: Factor w/ 4 levels "Other","Private",..: 3 3 3 3 3 3 3 3 4 3 ...
##  $ Dec : int  2 3 4 2 4 8 5 5 6 1 ...
##  $ Roll: int  318 200 455 86 577 329 637 395 438 201 ...

##了解資料型態：2571筆資料*六個變項
dim(dta)

## [1] 2571    6

Binning

## 新增Size變項，如果Roll2阿於中位數，命名為"Large"；反之為"Small"
dta$Size <- ifelse(dta$Roll > median(dta$Roll), "Large", "Small")

## 不顯示Size變項
dta$Size <- NULL

## 檢視前六筆資料
head(dta)

##     ID                  Name      City  Auth Dec Roll
## 1 1015      Hora Hora School Whangarei State   2  318
## 2 1052    Morningside School Whangarei State   3  200
## 3 1062        Onerahi School Whangarei State   4  455
## 4 1092 Raurimu Avenue School Whangarei State   2   86
## 5 1130      Whangarei School Whangarei State   4  577
## 6 1018       Hurupaki School Whangarei State   8  329

## 依照Roll做切割，分為"Small", "Mediam", "Large"
dta$Size <- cut(dta$Roll, 3, labels=c("Small", "Mediam", "Large"))

##　計算"Small", "Mediam", "Large"個數
table(dta$Size)

## 
##  Small Mediam  Large 
##   2555     15      1

## 先切割Size，再用sapply列出個數(結果同上)
dta.3 <- split(dta, dta$Size)
sapply(dta.3, function(x) length(x$Size))

##  Small Mediam  Large 
##   2555     15      1

Sorting

## 新增RollOrd變項，顯示Roll排名所在的位置
dta$RollOrd <- order(dta$Roll, decreasing=T)

## 顯示Roll排名前面的資料
head(dta[dta$RollOrd, ])

##       ID                  Name         City  Auth Dec Roll   Size RollOrd
## 1726 498 Correspondence School   Wellington State  NA 5546  Large     753
## 301   28     Rangitoto College     Auckland State  10 3022 Mediam     353
## 376   78      Avondale College     Auckland State   4 2613 Mediam     712
## 2307 319  Burnside High School Christchurch State   8 2588 Mediam     709
## 615   41      Macleans College     Auckland State  10 2476 Mediam    1915
## 199   43    Massey High School     Auckland State   5 2452 Mediam    1683

## 顯示Roll排名後面的資料
tail(dta[dta$RollOrd, ])

##        ID                    Name                  City    Auth Dec Roll  Size
## 2401 1641  Amana Christian School               Dunedin Private   9    7 Small
## 1590 2461       Tangimoana School              Manawatu   State   4    6 Small
## 1996 3598         Woodbank School              Kaikoura   State   4    6 Small
## 2112 3386     Jacobs River School          Jacobs River   State   5    6 Small
## 1514 2407     Ngamatapouri School Sth Taranaki District   State   9    5 Small
## 1575 2420 Papanui Junction School               Taihape   State   5    5 Small
##      RollOrd
## 2401    2562
## 1590     266
## 1996    2478
## 2112    1501
## 1514    2377
## 1575    1542

## 顯示City、Roll排名前面的資料
head(dta[order(dta$City, dta$Roll, decreasing=T), ])

##        ID                      Name      City  Auth Dec Roll  Size RollOrd
## 2548  401           Menzies College   Wyndham State   4  356 Small     859
## 2549 4054            Wyndham School   Wyndham State   5   94 Small    1163
## 1611 2742          Woodville School Woodville State   3  147 Small     726
## 1630 2640           Papatawa School Woodville State   7   27 Small    2273
## 2041 3600            Woodend School   Woodend State   9  375 Small    1401
## 1601  399 Central Southland College    Winton State   7  549 Small     450

## 顯示City、Roll排名後面的資料
tail(dta[order(dta$City, dta$Roll, decreasing=T), ])

##        ID                         Name    City  Auth Dec Roll  Size RollOrd
## 2169 3273                Albury School  Albury State   8   30 Small    1010
## 2018  350           Akaroa Area School  Akaroa State   8  125 Small    1051
## 2023 3332           Duvauchelle School  Akaroa State   9   41 Small     749
## 335  1200                Ahuroa School  Ahuroa State   7   22 Small     193
## 99   1000               Ahipara School Ahipara State   3  241 Small    1963
## 2117 2105 Awahono School - Grey Valley  Ahaura State   4  119 Small     364

Counting

## 計算Auth類別個數
table(dta$Auth)

## 
##            Other          Private            State State Integrated 
##                1               99             2144              327

## 先切割Auth，再用sapply列出個數(結果同上)
dta.2 <- split(dta, dta$Auth)
sapply(dta.2, function(x) length(x$Auth))

##            Other          Private            State State Integrated 
##                1               99             2144              327

## 將以上的table存入authtbl
authtbl <- table(dta$Auth); authtbl

## 
##            Other          Private            State State Integrated 
##                1               99             2144              327

## 檢視類別
class(authtbl)

## [1] "table"

## 檢視唯一一個Auth為"Other"的項目
dta[dta$Auth == "Other", ]

##       ID            Name         City  Auth Dec Roll  Size RollOrd
## 2315 518 Kingslea School Christchurch Other   1   51 Small    1579

## 產生Auth、Dec的次數交叉表
xtabs(~ Auth + Dec, data=dta)

##                   Dec
## Auth                 1   2   3   4   5   6   7   8   9  10
##   Other              1   0   0   0   0   0   0   0   0   0
##   Private            0   0   2   6   2   2   6  11  12  38
##   State            259 230 208 219 214 215 188 200 205 205
##   State Integrated  12  22  35  28  38  34  45  45  37  31

Aggregating

##計算Roll的平均
mean(dta$Roll)

## [1] 295.4737

##計算Auth是"Private"的Roll平均
mean(dta$Roll[dta$Auth == "Private"])

## [1] 308.798

## 依照Auth的分類計算Roll平均
aggregate(dta["Roll"], by=list(dta$Auth), FUN=mean)

##            Group.1     Roll
## 1            Other  51.0000
## 2          Private 308.7980
## 3            State 300.6301
## 4 State Integrated 258.3792

## 先切割Auth，再分類計算Roll平均(結果同上，但呈現方式不同)
dat.2 <- split(dta, dta$Auth)
sapply(dat.2, function(x) mean(x$Roll))

##            Other          Private            State State Integrated 
##          51.0000         308.7980         300.6301         258.3792

## 新增Rich變項，依Dec > 5為依據
dta$Rich <- dta$Dec > 5; head(dta$Rich)

## [1] FALSE FALSE FALSE FALSE FALSE  TRUE

##　依照Auth、Rich的分類計算Roll平均
aggregate(dta["Roll"], by=list(dta$Auth, dta$Rich), FUN=mean)

##            Group.1 Group.2     Roll
## 1            Other   FALSE  51.0000
## 2          Private   FALSE 151.4000
## 3            State   FALSE 261.7487
## 4 State Integrated   FALSE 183.2370
## 5          Private    TRUE 402.5362
## 6            State    TRUE 338.8243
## 7 State Integrated    TRUE 311.2135

##　依照Auth、Rich做切割，並計算Roll(結果同上)
dta.1 <- dta %>% group_by(Auth, Rich) %>% na.omit() %>% 
  summarize(Roll=mean(Roll))
dta.1

## # A tibble: 7 x 3
## # Groups:   Auth [4]
##   Auth             Rich   Roll
##   <fct>            <lgl> <dbl>
## 1 Other            FALSE   51 
## 2 Private          FALSE  151.
## 3 Private          TRUE   403.
## 4 State            FALSE  262.
## 5 State            TRUE   339.
## 6 State Integrated FALSE  183.
## 7 State Integrated TRUE   311.

## 依照Auth的分組，列出Roll的全距
by(dta["Roll"], INDICES=list(dta$Auth), FUN=range)

## : Other
## [1] 51 51
## ------------------------------------------------------------ 
## : Private
## [1]    7 1663
## ------------------------------------------------------------ 
## : State
## [1]    5 5546
## ------------------------------------------------------------ 
## : State Integrated
## [1]   18 1475

## 先切割Auth，再用lapply列出全距(結果同上)
dat <- split(dta, dta$Auth)
lapply(dat, function(x) range(x$Roll))

## $Other
## [1] 51 51
## 
## $Private
## [1]    7 1663
## 
## $State
## [1]    5 5546
## 
## $`State Integrated`
## [1]   18 1475

2020-04-27-In-class-4

VChang, C. Y.

2020-04-29

A case study

Binning

Sorting

Counting

Aggregating